FROM THE TRENCHES Issue №310

Practical decisions for AI and software

Technical guides to choose models, verify software and plan delivery.

Latest articles

New comparisons, practical guides and engineering lessons.

Vibe coder and junior developer taking different paths through an AI-assisted engineering system Leadership & Teams

Are Vibe Coders the New Junior Developers?

The traditional ticket-taking junior role is under pressure, but the junior developer is not extinct. Current labour data, the difference between prompting and engineering, and a hiring model for AI-native entry-level talent.

Kevin Riedl
Read
External QA benchmark for software defects found in the first 30 days Delivery & QA

External QA Benchmark: What We Find in the First 30 Days

A research-backed defect benchmark for permissions, regressions, browser/device combinations, data integrity, AI failures and production escapes, and why no honest universal bug-count median exists.

Christof Jori
Read
Programming languages converging into runtime, memory and architecture decisions Delivery & QA

Programming Languages Matter Less. Software Engineering Matters More.

AI makes syntax, boilerplate and cross-language translation cheap. It does not erase runtime, memory, concurrency, security or maintenance trade-offs. What CTOs and engineers should optimise for now.

Kevin Riedl
Read
Colibri streams GLM-5.2 experts from NVMe through RAM and VRAM on consumer hardware AI & Agents

Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.

Colibri now supports nine engine families and Brio closed-set scoring. Updated hardware requirements, the 372 GB versus 429 GB download discrepancy, real benchmark limits, GLM-5.3 support and a reproducible local API setup.

Kevin Riedl
Read
The future of enterprise software: AI-assisted systems engineering and verifiable computation Delivery & QA

The Future of Enterprise Software

Enterprise software can lose coherence through fragmentation. AI may reduce some systems-engineering work, while cryptographic methods can verify selected computations and records, not an entire architecture.

Alexandre Kotcherguine & Kevin Riedl
Read
Annotated software agency proposal showing the clauses that change price, scope and ownership Business & Regulation

Software Agency Proposal Teardown: 12 Clauses That Change Price, Scope and Ownership

A clause-by-clause teardown of a fictional EUR 96k software proposal: acceptance, IP, changes, warranty, dependencies, hosting, licences, handover, termination, security, subcontractors and done, with a downloadable 24-point review rubric.

Kevin Riedl
Read
x402 payment implementations compared across Coinbase, Stripe, Cloudflare, AWS and Circle Web3 & Privacy

x402 Payments in 2026: Coinbase, Stripe & Alternatives

x402 turns HTTP 402 into a payment negotiation for APIs, MCP tools and AI agents. Compare Coinbase, Stripe, Circle, Cloudflare, AWS, thirdweb, PayAI and self-hosting by layer, network, fee, compliance and production risk.

Kevin Riedl
Read
Open Knowledge Format packages organizational knowledge as portable Markdown for AI agents AI & Agents

Open Knowledge Format (OKF): The Enterprise Guide

OKF v0.2 turns company knowledge into linked Markdown and YAML with explicit provenance, trust, freshness, and attested computations. What changed, how to migrate, and where the format still stops.

Kevin Riedl
Read
Software maintenance cost benchmark for DACH SaaS: year one, two and three after launch Delivery & QA

What Software Maintenance Costs After Launch: A DACH SaaS Benchmark

Observed post-launch maintenance cost bands for DACH SaaS: year-one, year-two and year-three spend split across bug fixes, dependency upgrades, cloud, observability, security, compliance, support, product iteration and emergency work, with an interactive calculator.

Kevin Riedl
Read
Inbox, without the noise

Get the next field note

One concise email when we publish. No tracking pixels, and no inbox filler.